Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add southleft/skills-for-figma --skill deep-component-figmagit clone --depth 1 https://github.com/southleft/skills-for-figmaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/southleft/skills-for-figma/deep-component-figma)<a href="https://agentmods.dev/skills/southleft/skills-for-figma/deep-component-figma"><img src="https://agentmods.dev/badge/skills/southleft/skills-for-figma/deep-component-figma/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/southleft/skills-for-figma/deep-component-figma"><img src="https://agentmods.dev/badge/skills/southleft/skills-for-figma/deep-component-figma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00158 | $0.01179 |
| Opus 5 | $0.00079 | $0.00589 |
| Sonnet 5 | $0.00032 | $0.00236 |
| Haiku 4.5 | $0.00016 | $0.00118 |
Grade A, and why
deep-component-figma scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deep-component-figma — unlimited-depth tree with resolved tokens
Walk one node (usually a COMPONENT / COMPONENT_SET / INSTANCE, but any node works) recursively
to a depth you choose, capturing at every level: layout (auto-layout, padding, spacing, sizing),
visual properties (fills, strokes, stroke weight, corner radius, effects, opacity), typography for
text nodes, boundVariables resolved to token names + code syntax, INSTANCE main-component
references (including whether the main is a variant and its set), prototype reactions, and dev-mode
annotations. This is the richest single-component read for high-fidelity code generation.
Skill boundaries
use_figmarules — load the officialfigma-useskill first; it is the full Figma Plugin API reference. Essentials these scripts rely on: plain JS with top-levelawait+return(no IIFE, nofigma.closePlugin();console.logis not returned), inputs inlined asconstat the top of each script, colors in 0–1 range, load fonts before any text op,await figma.getNodeByIdAsync(...), and atomic errors (a failed script applies nothing — read the error, fix, retry).- Whole-file inventory (all tokens/components/styles at once) → use
design-system-inventory-figma. - Variant set as a CSS state machine (per-state diffs, pseudo-class mapping) →
use
analyze-component-set-figma. - This depth of tree + resolved tokens + reactions is not what the native MCP's
get_design_context(rendered single-selection summary) orget_metadata(flat structure) return — it is a design-system code-gen capability layered on top.
Workflow
- Get the node id. From selection (
figma_get_selection), search, or a pasted id. - Choose a depth. Set
const DEPTH(default 10). Deep design components rarely exceed ~6 levels; use a smaller number first to keep the payload manageable, then go deeper if needed. - Run
scripts/deep-component.jsviause_figma(skillNames: "deep-component-figma"). Setconst NODE_IDandconst DEPTHat the top. - Generate code. The returned tree mirrors the DOM you should build. Prefer
boundVariablestoken names (and theircodeSyntax) over raw hex; usemainComponentrefs to reuse imported components; usereactionsto wire up interaction/navigation. - If the payload is too big, lower
DEPTH(nodes past the limit are summarized with achildCount+_depthLimitReachedmarker) or target a smaller sub-node id.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 59 lines · 158 tokens per session scan A ebad643d573b
deep-component-figma is a skill published in the GitHub repository southleft/skills-for-figma (14 stars, last pushed 3mo ago), licensed MIT. It adds 158 tokens to every session and 1,179 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
system-pitch
Write a design system investment pitch with a business case and ROI framing. Trigger when someone says: pitch the design system, make the case for the system, sell this to leadership, justify the investment, business case for design systems, why should we invest in a design system, or anything about building an…
token-audit
Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…
ai-component-description
Generate AI-optimised text descriptions for components, formatted for Figma's MCP server and LLM consumption. This produces prose descriptions in a six-section format (purpose, props, anti-patterns, composition, accessibility, examples), NOT JSON schemas or structured data files. Trigger when someone says: write…
context-engine-builder
Generate a context engine — seven structured blueprint files (UX, UI, content, accessibility, ethical, technical, business intelligence) that encode everything an AI agent needs to work with a design system. This produces YAML infrastructure in .ai/context-engine/, NOT a health score or quality assessment. Trigger…
stakeholder-brief
Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…
token-compliance
Check a codebase or implementation for token compliance — finding hardcoded values, wrong-tier token references, and inconsistent token application in consuming code. This checks how tokens are used in code, NOT how the tokens themselves are defined or structured. Trigger when someone says: are we using tokens…